Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    prepositions and words related to technology products

    oai_token-act-pair · gpt-3.5-turbo

    important concepts or statements related to causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    creen
    -0.74
     hostage
    -0.74
     filing
    -0.72
    antics
    -0.71
     deadline
    -0.67
     release
    -0.66
    stress
    -0.64
     compromise
    -0.64
     bracket
    -0.64
     Badge
    -0.63
    POSITIVE LOGITS
    kson
    1.02
    Ò
    0.83
    Austral
    0.78
    hs
    0.78
    ryu
    0.77
    ORGE
    0.73
    john
    0.73
    TX
    0.69
    Gov
    0.69
     constitu
    0.69
    Act Density 0.000%

    No Known Activations